{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JAV723NTLWJSZK522UY3GCVCZW","short_pith_number":"pith:JAV723NT","schema_version":"1.0","canonical_sha256":"482bfd6db35d932cabbad531b30aa2cdb1c453e8ce1c3df4d293e862a1bb7da0","source":{"kind":"arxiv","id":"1911.08701","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Curiosity for Efficient Exploration in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Ramos, Lionel Ott, Tom Blau","submitted_at":"2019-11-20T04:30:20Z","abstract_excerpt":"Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\\epsilon$-greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that have already been explored. We introduce a novel method based on Bayesian linear regression and latent space embedding to generate an intrinsic reward signal that encourages the learning agent to seek out unexplored parts of the state space. This method is computationally ef"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.08701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T04:30:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08f88db93ac9d59bec4a1bbff0754cf7fae5e2d434905737195481f3f8055db3","abstract_canon_sha256":"121cc0ae81ecfa39de56d40b4d77be4ff1c29c84a62e16f3eb967a7ae2428a1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:35.328277Z","signature_b64":"SNqPK2pp7vYb4lDw+mXBM/GMyq9LV/Cr+WCiigEbXgvJnAAuEldMb/x7a4SQ3kjh+6Fo9RBPNyALVrJxih5MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"482bfd6db35d932cabbad531b30aa2cdb1c453e8ce1c3df4d293e862a1bb7da0","last_reissued_at":"2026-07-05T00:20:35.327868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:35.327868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Curiosity for Efficient Exploration in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Ramos, Lionel Ott, Tom Blau","submitted_at":"2019-11-20T04:30:20Z","abstract_excerpt":"Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\\epsilon$-greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that have already been explored. We introduce a novel method based on Bayesian linear regression and latent space embedding to generate an intrinsic reward signal that encourages the learning agent to seek out unexplored parts of the state space. This method is computationally ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08701","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.08701/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.08701","created_at":"2026-07-05T00:20:35.327930+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.08701v1","created_at":"2026-07-05T00:20:35.327930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08701","created_at":"2026-07-05T00:20:35.327930+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAV723NTLWJS","created_at":"2026-07-05T00:20:35.327930+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAV723NTLWJSZK52","created_at":"2026-07-05T00:20:35.327930+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAV723NT","created_at":"2026-07-05T00:20:35.327930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25438","citing_title":"Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08418","citing_title":"Exploring Temporal Representation in Neural Processes for Multimodal Action Prediction","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW","json":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW.json","graph_json":"https://pith.science/api/pith-number/JAV723NTLWJSZK522UY3GCVCZW/graph.json","events_json":"https://pith.science/api/pith-number/JAV723NTLWJSZK522UY3GCVCZW/events.json","paper":"https://pith.science/paper/JAV723NT"},"agent_actions":{"view_html":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW","download_json":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW.json","view_paper":"https://pith.science/paper/JAV723NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.08701&json=true","fetch_graph":"https://pith.science/api/pith-number/JAV723NTLWJSZK522UY3GCVCZW/graph.json","fetch_events":"https://pith.science/api/pith-number/JAV723NTLWJSZK522UY3GCVCZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/action/storage_attestation","attest_author":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/action/author_attestation","sign_citation":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/action/citation_signature","submit_replication":"https://pith.science/pith/JAV723NTLWJSZK522UY3GCVCZW/action/replication_record"}},"created_at":"2026-07-05T00:20:35.327930+00:00","updated_at":"2026-07-05T00:20:35.327930+00:00"}